• Asian-Australasian Journal of Animal Sciences
• /
• v.11 no.5
• /
• pp.580-585
• /
• 1998

The study was conducted to determine if variation in protein yield can be explained by expressions of early lactation somatic cell score (SCS) and if prediction can be improved by including SCS among the predictors. A data set was prepared (n = 663,438) from Wisconsin Dairy Improvement Association (USA) records for protein yield with sample days near 20. Stepwise regression was used requiring F statistic (p < .01) for any variable to stay in the model. Separate analyses were run for 12 combinations of four seasons and first three parities. Selection of SCS variables was not consistent across seasons or lactations. Coefficients of detennination ($R^2$) ranged from 51 to 61% with higher values for earlier lactations. Including any expression of SCS in the prediction equations improved $R^2$ by < 1 %. SCS was associated with milk yield on the sample day, but the association was not strong enough to improve the prediction of future yield when other expressions of milk yield were in the model.

• Asian-Australasian Journal of Animal Sciences
• /
• v.28 no.7
• /
• pp.993-998
• /
• 2015

Possibilities of predicting eggshell ultrastructure from direct non-destructive and destructive measurements were examined using 120 Fayoumi eggs collected from the flock at 45 weeks of age. The non-destructive measurements included weight, length and width of the egg. The destructive measurements were breaking strength and shell thickness. The eggshell ultrastructure traits involved the total thickness of eggshell layer, thickness of palisade layer, cone layer and total score. Prediction of total thickness of eggshell layer based on non-destructive measurements individually or simultaneously was not possible ($R^2=0.01$ to 0.16). The destructive measurements were far more accurate than the non-destructive in predicting total thickness of eggshell layer. Prediction based on breaking strength alone was more accurate ($R^2=0.85$) than that based on shell thickness alone ($R^2=0.72$). Adding shell thickness to breaking strength (the best predictor) increased the accuracy of prediction by 5%. The results obtained indicated that both non-destructive and destructive measurements were not useful in predicting the cone layer ($R^2$ not exceeded 18%). The maximum accuracy of prediction of total score ($R^2=0.48$) was obtained from prediction based on breaking strength alone. Combining shell thicknesses and breaking strength into one equation was no help in improving the accuracy of prediction.

• Journal of Korean Society of Forest Science
• /
• v.103 no.2
• /
• pp.233-239
• /
• 2014

This study was carried out to propose the criteria for the prediction of landslide occurrence through analysis the influence of each factor by using the quantification theory. The results obtained from this study are summarized as follows. From a stepwise regression analysis between the landslide area($m^2$) and environmental factors, the factors strongly affecting the landslide sediment($m^2$) were the Parents rock (igneous), cross slope(complex), coniferous forests (forest type) and slope gradient ($21{\sim}30^{\circ}$). According to the range, it was shown in order of Cross slope (0.2922), Parents rock (0.2691), Forest type (0.2631) and Slope gradient (0.2312). The range of prediction score of landslide occurrence has been distributed between score 0 and score 1.0556, the median value was score 0.5278. The prediction for class I was over 0.7818, for class II was 0.5279 to 0.7917, for class III 0.2694 to 0.5278 and for class IV was below 0.2693. The prediction on landslide occurrence appeared relatively high accuracy rate as 72% for class I and II. Therefore, this score table for landslide will be very useful for judgement of dangerous slope.

• Korean Journal of Materials Research
• /
• v.33 no.4
• /
• pp.164-174
• /
• 2023

The bandgap characteristics of semiconductor materials are an important factor when utilizing semiconductor materials for various applications. In this study, based on data provided by AFLOW (Automatic-FLOW for Materials Discovery), the bandgap of a semiconductor material was predicted using only the material's compositional features. The compositional features were generated using the python module of 'Pymatgen' and 'Matminer'. Pearson's correlation coefficients (PCC) between the compositional features were calculated and those with a correlation coefficient value larger than 0.95 were removed in order to avoid overfitting. The bandgap prediction performance was compared using the metrics of R² score and root-mean-squared error. By predicting the bandgap with randomforest and xgboost as representatives of the ensemble algorithm, it was found that xgboost gave better results after cross-validation and hyper-parameter tuning. To investigate the effect of compositional feature selection on the bandgap prediction of the machine learning model, the prediction performance was studied according to the number of features based on feature importance methods. It was found that there were no significant changes in prediction performance beyond the appropriate feature. Furthermore, artificial neural networks were employed to compare the prediction performance by adjusting the number of features guided by the PCC values, resulting in the best R² score of 0.811. By comparing and analyzing the bandgap distribution and prediction performance according to the material group containing specific elements (F, N, Yb, Eu, Zn, B, Si, Ge, Fe Al), various information for material design was obtained.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.265-282
• /
• 2022

Sea surface temperature (SST) is a factor that greatly influences ocean circulation and ecosystems in the Earth system. As global warming causes changes in the SST near the Korean Peninsula, abnormal water temperature phenomena (high water temperature, low water temperature) occurs, causing continuous damage to the marine ecosystem and the fishery industry. Therefore, this study proposes a methodology to predict the SST near the Korean Peninsula and prevent damage by predicting abnormal water temperature phenomena. The study area was set near the Korean Peninsula, and ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF) was used to utilize SST data at the same time period. As a research method, Long Short-Term Memory (LSTM) algorithm specialized for time series data prediction among deep learning models was used in consideration of the time series characteristics of SST data. The prediction model predicts the SST near the Korean Peninsula after 1- to 7-days and predicts the high water temperature or low water temperature phenomenon. To evaluate the accuracy of SST prediction, Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) indicators were used. The summer (JAS) 1-day prediction result of the prediction model, R²=0.996, RMSE=0.119℃, MAPE=0.352% and the winter (JFM) 1-day prediction result is R²=0.999, RMSE=0.063℃, MAPE=0.646%. Using the predicted SST, the accuracy of abnormal sea surface temperature prediction was evaluated with an F1 Score (F1 Score=0.98 for high water temperature prediction in summer (2021/08/05), F1 Score=1.0 for low water temperature prediction in winter (2021/02/19)). As the prediction period increased, the prediction model showed a tendency to underestimate the SST, which also reduced the accuracy of the abnormal water temperature prediction. Therefore, it is judged that it is necessary to analyze the cause of underestimation of the predictive model in the future and study to improve the prediction accuracy.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.323-325
• /
• 2021

In this article, we have improved the prediction of hypertension detection using the feature selection method for the Korean national health data named by the KNHANES database. The study identified a variety of risk factors associated with chronic hypertension. The paper is divided into two modules. The first of these is a data pre-processing step that uses a factor analysis (FA) based feature selection method from the dataset. The next module applies a predictive analysis step to detect and predict hypertension risk prediction. In this study, we compare the mean standard error (MSE), F1-score, and area under the ROC curve (AUC) for each classification model. The test results show that the proposed FIFA-OE-NB algorithm has an MSE, F1-score, and AUC outcomes 0.259, 0.460, and 64.70%, respectively. These results demonstrate that the proposed FIFA-OE method outperforms other models for hypertension risk predictions.

• Journal of Korean Critical Care Nursing
• /
• v.8 no.1
• /
• pp.71-79
• /
• 2015

Purpose: The purpose of this study was to compare the applicability of the Charlson Comorbidity Index (CCI) and Acute Physiology, Age, Chronic Health Evaluation III (APACHE III) to the prediction of the healthcare outcomes of intensive care unit (ICU) patients. Methods: This research was performed with 136 adult patients (age>18 years) who were admitted to the ICU between May and June 2012. Data were measured using the CCI score with a comorbidity index of 19 and the APACHE III score on the standard of the worst result with vital signs and laboratory results. Discrimination was evaluated using receiver operating characteristic (ROC) curves and area under an ROC curve (AUC). Calibration was performed using logistic regression. Results: The overall mortality was 25.7%. The mean CCI and APACHE III scores for survivors were found to be significantly lower than those of non-survivors. The AUC was 0.835 for the APACHE III score and remained high, at 0.688, for the CCI score. The rate of concordance according to the CCI and the APACHE III score was 69.1%. Conclusion: The route of admission, days in ICU, CCI, and APACHE III score are associated with an increased mortality risk in ICU patients.

• Journal of Oriental Neuropsychiatry
• /
• v.22 no.3
• /
• pp.13-22
• /
• 2011

Objectives : This study was to research the relationship between Hwa-Byung and Framingham coronary risk score(FRS), cardiovascular disease. Methods : 649 people participated in the community based cohort study in Wonju City of South Korea from July 2nd to August 30th in 2006. Educated investigators checked up systolic & diastolic blood pressure and surveyed Hwa-Byung Diagnostic Interview Schedule(HBDIS), cohort questionnaire about gender, age, smoking, diabetes. Blood sample was collected from participants to analyze total cholesterol, HDL-cholesterol. FRS was calculated from collected data. 10-year prediction of coronary heart disease was determined from FRS by using score sheet that is estimated by Wilson et al. Collected data were analyzed by the chi-square test. Results : 1. Low risk number of people was 18(52.9%) in Hwa-Byung group, 263(42.8%) in non Hwa-Byung group. p-value was 0.472. Difference of the two group was invalid. 2. The number of people below or equal to average 10-year prediction of coronary heart disease as gnder & age, Hwa-Byung group was 19(55.9%), non Hwa-Byung group was 412(67.0%). p-value was 0.251. Difference of the two group was invalid. Conclusions : There was no correlationship Between Hwa-Byung and 10-year prediction of coronary heart disease.

• Journal of Ocean Engineering and Technology
• /
• v.36 no.5
• /
• pp.295-302
• /
• 2022

The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.